Related papers: Mutual Information Preserving Neural Network Pruni…
Generative modeling has recently undergone remarkable advancements, primarily propelled by the transformative implications of Diffusion Probabilistic Models (DPMs). The impressive capability of these models, however, often entails…
Computer-assisted treatment has emerged as a viable application of medical imaging, owing to the efficacy of deep learning models. Real-time inference speed remains a key requirement for such applications to help medical personnel. Even…
Neural networks can be compressed to reduce memory and computational requirements, or to increase accuracy by facilitating the use of a larger base architecture. In this paper we focus on pruning individual neurons, which can simultaneously…
We show how solution concepts from cooperative game theory can be used to tackle the problem of pruning neural networks. The ever-growing size of deep neural networks (DNNs) increases their performance, but also their computational…
We explore the effect of introducing prior information into the intermediate level of neural networks for a learning task on which all the state-of-the-art machine learning algorithms tested failed to learn. We motivate our work from the…
Recent advancements in large language models have intensified the need for efficient and deployable models within limited inference budgets. Structured pruning pipelines have shown promise in token efficiency compared to training…
The widespread availability of pre-trained vision models has enabled numerous deep learning applications through their transferable representations. However, their computational and storage costs often limit practical deployment.…
Deep neural networks are often highly overparameterized, prohibiting their use in compute-limited systems. However, a line of recent works has shown that the size of deep networks can be considerably reduced by identifying a subset of…
Federated Learning (FL) represents a growing machine learning (ML) paradigm designed for training models across numerous nodes that retain local datasets, all without directly exchanging the underlying private data with the parameter server…
Although 3D Convolutional Neural Networks (CNNs) are essential for most learning based applications involving dense 3D data, their applicability is limited due to excessive memory and computational requirements. Compressing such networks by…
We study the neural network (NN) compression problem, viewing the tension between the compression ratio and NN performance through the lens of rate-distortion theory. We choose a distortion metric that reflects the effect of NN compression…
The advent of sparsity inducing techniques in neural networks has been of a great help in the last few years. Indeed, those methods allowed to find lighter and faster networks, able to perform more efficiently in resource-constrained…
Traditional (unstructured) pruning methods for a Transformer model focus on regularizing the individual weights by penalizing them toward zero. In this work, we explore spectral-normalized identity priors (SNIP), a structured pruning…
Neural networks are commonly trained in highly overparameterized regimes, yet empirical evidence consistently shows that many parameters become redundant during learning. Most existing pruning approaches impose sparsity through explicit…
Quantization, knowledge distillation, and magnitude pruning are among the most popular methods for neural network compression in NLP. Independently, these methods reduce model size and can accelerate inference, but their relative benefit…
Deep Neural Networks (DNNs) are usually over-parameterized, causing excessive memory and interconnection cost on the hardware platform. Existing pruning approaches remove secondary parameters at the end of training to reduce the model size;…
Deep pre-trained Transformer models have achieved state-of-the-art results over a variety of natural language processing (NLP) tasks. By learning rich language knowledge with millions of parameters, these models are usually…
By removing parameters from deep neural networks, unstructured pruning methods aim at cutting down memory footprint and computational cost, while maintaining prediction accuracy. In order to tackle this otherwise intractable problem, many…
Pruning can be an effective method of compressing large pre-trained models for inference speed acceleration. Previous pruning approaches rely on access to the original training dataset for both pruning and subsequent fine-tuning. However,…
Adversarial pruning compresses models while preserving robustness. Current methods require access to adversarial examples during pruning. This significantly hampers training efficiency. Moreover, as new adversarial attacks and training…